{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FGGWVUKIYA3YX7KHWKYW2QZEPW","short_pith_number":"pith:FGGWVUKI","canonical_record":{"source":{"id":"2310.16776","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T17:06:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"879a49293f184576e192d6d92d587f50b0107ddf68f5820975941d7c69278c0a","abstract_canon_sha256":"caf9af3794e01609edc6862d30e03f9e827e3ce0cb587ba2476197c009515fe1"},"schema_version":"1.0"},"canonical_sha256":"298d6ad148c0378bfd47b2b16d43247dae7ac4919c2861665f91846114ba3a4d","source":{"kind":"arxiv","id":"2310.16776","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16776","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16776v5","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16776","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"pith_short_12","alias_value":"FGGWVUKIYA3Y","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"pith_short_16","alias_value":"FGGWVUKIYA3YX7KH","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"pith_short_8","alias_value":"FGGWVUKI","created_at":"2026-07-05T08:31:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FGGWVUKIYA3YX7KHWKYW2QZEPW","target":"record","payload":{"canonical_record":{"source":{"id":"2310.16776","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T17:06:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"879a49293f184576e192d6d92d587f50b0107ddf68f5820975941d7c69278c0a","abstract_canon_sha256":"caf9af3794e01609edc6862d30e03f9e827e3ce0cb587ba2476197c009515fe1"},"schema_version":"1.0"},"canonical_sha256":"298d6ad148c0378bfd47b2b16d43247dae7ac4919c2861665f91846114ba3a4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:06.540726Z","signature_b64":"p4NlspxuDKupLPzJayaLBJAcHkctZRUiVnvNUOF2PqTLiMNI+2F0S+kfpu/VkSrM12LfVkQ8NNgRFm6EVOu7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"298d6ad148c0378bfd47b2b16d43247dae7ac4919c2861665f91846114ba3a4d","last_reissued_at":"2026-07-05T08:31:06.540333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:06.540333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.16776","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:31:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wjMZyXxyfxYuA0/KdjYLhM4U7izgCSaXhetz/+GbxQBALze2ZqoaM+ykjR6y7hjr5BVNIuTG5iWXQ42M5gm6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T00:20:32.468022Z"},"content_sha256":"00c309cea0d0bca1fef0ff06c6bbc94d8804c7c9f0f30bc639620481691b00c3","schema_version":"1.0","event_id":"sha256:00c309cea0d0bca1fef0ff06c6bbc94d8804c7c9f0f30bc639620481691b00c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FGGWVUKIYA3YX7KHWKYW2QZEPW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DEFT: Data Efficient Fine-Tuning for Pre-Trained Language Models via Unsupervised Core-Set Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Devleena Das, Vivek Khetan","submitted_at":"2023-10-25T17:06:42Z","abstract_excerpt":"Recent advances have led to the availability of many pre-trained language models (PLMs); however, a question that remains is how much data is truly needed to fine-tune PLMs for downstream tasks? In this work, we introduce DEFT-UCS, a data-efficient fine-tuning framework that leverages unsupervised core-set selection to identify a smaller, representative dataset that reduces the amount of data needed to fine-tune PLMs for downstream tasks. We examine the efficacy of DEFT-UCS in the context of text-editing LMs, and compare to the state-of-the art text-editing model, CoEDIT. Our results demonstra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16776","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.16776/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:31:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FxJIe+VAdUjQNqjVyTDudUYEHGwBf289VF6f17kosU1h/SNSANuw64B1MDBFZkjYhK52xfeeC9adGT2d3/Z2Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T00:20:32.469016Z"},"content_sha256":"7c9feb04d2d81c5767b79f11708b5e7dcd14de93823621e22dba54dbc5a9a86a","schema_version":"1.0","event_id":"sha256:7c9feb04d2d81c5767b79f11708b5e7dcd14de93823621e22dba54dbc5a9a86a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGGWVUKIYA3YX7KHWKYW2QZEPW/bundle.json","state_url":"https://pith.science/pith/FGGWVUKIYA3YX7KHWKYW2QZEPW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGGWVUKIYA3YX7KHWKYW2QZEPW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T00:20:32Z","links":{"resolver":"https://pith.science/pith/FGGWVUKIYA3YX7KHWKYW2QZEPW","bundle":"https://pith.science/pith/FGGWVUKIYA3YX7KHWKYW2QZEPW/bundle.json","state":"https://pith.science/pith/FGGWVUKIYA3YX7KHWKYW2QZEPW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGGWVUKIYA3YX7KHWKYW2QZEPW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FGGWVUKIYA3YX7KHWKYW2QZEPW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"caf9af3794e01609edc6862d30e03f9e827e3ce0cb587ba2476197c009515fe1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T17:06:42Z","title_canon_sha256":"879a49293f184576e192d6d92d587f50b0107ddf68f5820975941d7c69278c0a"},"schema_version":"1.0","source":{"id":"2310.16776","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16776","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16776v5","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16776","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"pith_short_12","alias_value":"FGGWVUKIYA3Y","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"pith_short_16","alias_value":"FGGWVUKIYA3YX7KH","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"pith_short_8","alias_value":"FGGWVUKI","created_at":"2026-07-05T08:31:06Z"}],"graph_snapshots":[{"event_id":"sha256:7c9feb04d2d81c5767b79f11708b5e7dcd14de93823621e22dba54dbc5a9a86a","target":"graph","created_at":"2026-07-05T08:31:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.16776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances have led to the availability of many pre-trained language models (PLMs); however, a question that remains is how much data is truly needed to fine-tune PLMs for downstream tasks? In this work, we introduce DEFT-UCS, a data-efficient fine-tuning framework that leverages unsupervised core-set selection to identify a smaller, representative dataset that reduces the amount of data needed to fine-tune PLMs for downstream tasks. We examine the efficacy of DEFT-UCS in the context of text-editing LMs, and compare to the state-of-the art text-editing model, CoEDIT. Our results demonstra","authors_text":"Devleena Das, Vivek Khetan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T17:06:42Z","title":"DEFT: Data Efficient Fine-Tuning for Pre-Trained Language Models via Unsupervised Core-Set Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16776","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:00c309cea0d0bca1fef0ff06c6bbc94d8804c7c9f0f30bc639620481691b00c3","target":"record","created_at":"2026-07-05T08:31:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"caf9af3794e01609edc6862d30e03f9e827e3ce0cb587ba2476197c009515fe1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T17:06:42Z","title_canon_sha256":"879a49293f184576e192d6d92d587f50b0107ddf68f5820975941d7c69278c0a"},"schema_version":"1.0","source":{"id":"2310.16776","kind":"arxiv","version":5}},"canonical_sha256":"298d6ad148c0378bfd47b2b16d43247dae7ac4919c2861665f91846114ba3a4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"298d6ad148c0378bfd47b2b16d43247dae7ac4919c2861665f91846114ba3a4d","first_computed_at":"2026-07-05T08:31:06.540333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:06.540333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p4NlspxuDKupLPzJayaLBJAcHkctZRUiVnvNUOF2PqTLiMNI+2F0S+kfpu/VkSrM12LfVkQ8NNgRFm6EVOu7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:06.540726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16776","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00c309cea0d0bca1fef0ff06c6bbc94d8804c7c9f0f30bc639620481691b00c3","sha256:7c9feb04d2d81c5767b79f11708b5e7dcd14de93823621e22dba54dbc5a9a86a"],"state_sha256":"1020d9e50af601bfebe09f33d8d3f7a34d74bc67bcb61d3db118690aa68ee8ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1DyzsqZEUArHRHy4mNixX3lcdojegYHUHwDyMkbvLrPd8S4DyTL224FKXe1I8EgUql4DCKPn9/Y8KyEFNswTCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T00:20:32.475146Z","bundle_sha256":"8730426ec4382e7029ca12628fec7103acd8e1dd05a8e01cf42dbcacf8b7abfc"}}